Yeonsung Jung

Co-Evolving Agents: Learning from Failures as Hard Negatives

Web Agents Are Still Greedy: Progress-Aware Action Generation and Selection via Meta-Plan

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Playing the Fool: Jailbreaking Large Language Models with Out-of-Distribution Strategies

MeZO-A$^{3}$dam: Memory-efficient Zeroth-order Adam with Adaptivity Adjustments for Fine-tuning LLMs

Augmentation-Driven Metric for Balancing Preservation and Modification in Text-Guided Image Editing